Fast and accurate mapping of fine scale abundance of a VME in the deep sea with computer vision

Current velocity, water quality, and benthic taxa as predictors for coral recruitment rates on the Great Barrier Reef

Coral reefs worldwide are experiencing frequent disturbances, rendering coral recruitment critical for population recovery. This large-scale study identifies environmental, spatial, and biotic drivers of coral recruit densities at 141 stations stratified across seven regions and three depths (1, 5, and 15 m depths) with contrasting environmental conditions across and along the Great Barrier Reef and the Torres Strait. Settlement tiles were deployed for two years, with coral densities and benthic cover quantified following retrieval. Benthic communities were assessed from tile images using the point-classification AI program ReefCloud. Environmental data were derived from in situ readings and environmental models. Across all sites, coral recruit densities averaged 187 ±  12 m‒2 (SE), with region-wide averages ranging from 43.5 ±  12 m‒2 to 247 ±  32 m‒2. Mean densities were 3-fold higher in the four clear-water regions compared to the three turbid-water regions. Boosted regression tree analyses showed that densities declined with increasing current velocity, sedimentation, and depth, and increased with increasing pH. From lowest to highest observed levels of current velocity, recruit densities declined by ~ 530 m‒2. From lowest to highest sedimentation, densities declined by ~ 300 recruits m‒2. Even relatively minor increases in sediment deposits from 0.1 to 38 mg cm‒2 were associated with a monotonic decline of ~ 130 recruits m‒2. Recruit densities were also weakly positively related to the cover of turf and crustose coralline algae on tile tops, and negatively related to fleshy invertebrate cover on the tile undersides. Some variation in the cover of these benthic taxa was also related to environmental conditions (e.g., sedimentation and currents), suggesting the possibility of additional indirect environmental effects on recruit densities. Our results highlight the strong role of current velocity and water quality as regulators of coral recruitment success, likely influencing the capacity of reef sites to recover after a disturbance.

New interactive machine learning tool for marine image analysis

Advancing imaging technologies are drastically increasing the rate of marine video and image data collection. Often these datasets are not analysed to their full potential as extracting information for multiple species is incredibly time-consuming. This study demonstrates the capability of the open-source interactive machine learning tool, RootPainter, to analyse large marine image datasets quickly and accurately. The ability of RootPainter to extract the presence and surface area of the cold-water coral reef associate sponge species, Mycale lingua, was tested in two datasets: 18 346 time-lapse images and 1420 remotely operated vehicle video frames. New corrective annotation metrics integrated with RootPainter allow objective assessment of when to stop model training and reduce the need for manual model validation. Three highly accurate M. lingua models were created using RootPainter, with an average dice score of 0.94 ± 0.06. Transfer learning aided the production of two of the models, increasing analysis efficiency from 6 to 16 times faster than manual annotation for time-lapse images. Surface area measurements were extracted from both datasets allowing future investigation of sponge behaviours and distributions. Moving forward, interactive machine learning tools and model sharing could dramatically increase image analysis speeds, collaborative research and our understanding of spatiotemporal patterns in biodiversity.

Cost-effort analysis of Baited Remote Underwater Video (BRUV) and environmental DNA (eDNA) in monitoring marine ecological communities

Monitoring the diversity and distribution of species in an ecosystem is essential to assess the success of restoration strategies. Implementing biomonitoring methods, which provide a comprehensive assessment of species diversity and mitigate biases in data collection, holds significant importance in biodiversity research. Additionally, ensuring that these methods are cost-efficient and require minimal effort is crucial for effective environmental monitoring. In this study we compare the efficiency of species detection, the cost and the effort of two non-destructive sampling techniques: Baited Remote Underwater Video (BRUV) and environmental DNA (eDNA) metabarcoding to survey marine vertebrate species. Comparisons were conducted along the Sussex coast upon the introduction of the Nearshore Trawling Byelaw. This Byelaw aims to boost the recovery of the dense kelp beds and the associated biodiversity that existed in the 1980s. We show that overall BRUV surveys are more affordable than eDNA, however, eDNA detects almost three times as many species as BRUV. eDNA and BRUV surveys are comparable in terms of effort required for each method, unless eDNA analysis is carried out externally, in which case eDNA requires less effort for the lead researchers. Furthermore, we show that increased eDNA replication yields more informative results on community structure. We found that using both methods in conjunction provides a more complete view of biodiversity, with BRUV data supplementing eDNA monitoring by recording species missed by eDNA and by providing additional environmental and life history metrics. The results from this study will serve as a baseline of the marine vertebrate community in Sussex Bay allowing future biodiversity monitoring research projects to understand community structure as the ecosystem recovers following the removal of trawling fishing pressure. Although this study was regional, the findings presented herein have relevance to marine biodiversity and conservation monitoring programs around the globe.

Underwater Holothurian Target-Detection Algorithm Based on Improved CenterNet and Scene Feature Fusion

Aiming at the common problems, such as noise pollution, low contrast, and color distortion in underwater images, and the characteristics of holothurian recognition, such as morphological ambiguity, high similarity with the background, and coexistence of special ecological scenes, this paper proposes an underwater holothurian target-detection algorithm (FA-CenterNet), based on improved CenterNet and scene feature fusion. First, to reduce the model's occupancy of embedded device resources, we use EfficientNet-B3 as the backbone network to reduce the model's Params and FLOPs. At the same time, EfficientNet-B3 increases the depth and width of the model, which improves the accuracy of the model. Then, we design an effective FPT (feature pyramid transformer) combination module to fully focus and mine the information on holothurian ecological scenarios of different scales and spaces (e.g., holothurian spines, reefs, and waterweeds are often present in the same scenario as holothurians). The co-existing scene information can be used as auxiliary features to detect holothurians, which can improve the detection ability of fuzzy and small-sized holothurians. Finally, we add the AFF module to realize the deep fusion of the shallow-detail and high-level semantic features of holothurians. The results show that the method presented in this paper yields better results on the 2020 CURPC underwater target-detection image dataset with an AP50 of 83.43%, Params of 15.90 M, and FLOPs of 25.12 G compared to other methods. In the underwater holothurian-detection task, this method improves the accuracy of detecting holothurians with fuzzy features, a small size, and dense scene. It also achieves a good balance between detection accuracy, Params, and FLOPs, and is suitable for underwater holothurian detection in most situations.